Anthropomorphism plays a crucial role in human-computer interaction (HCI), robotics, and, in my case of interest, artificial intelligence (AI) chatbots. People commonly anthropomorphize nonhuman agents such as pets and gods, imbuing humanlike capacities and mental experiences to them. According to prior research, there are three psychological determinants that underlie anthropomorphism when individuals try to comprehend such agents: elicited agent knowledge, effectance motivation, and sociality motivation. Since existing research on chatbot anthropomorphism has not kept pace with advancements in AI technology, particularly the increasing sophistication of LLMs, I will test whether chatbot predictability and users' levels of loneliness influence the anthropomorphization of AI chatbots using an experimental method. The experiment is not only relevant for obtaining new empirical results that support the cognitive and motivational determinants of anthropomorphism but also contributes to the discussion on the impact of AI chatbot design.